The parameters 'exo_dim' and 'exo_shape' in the class 'NBeatsNet'

philipperemy / n-beats

Keras/Pytorch implementation of N-BEATS: Neural basis expansion analysis for interpretable time series forecasting.

MIT License

864 stars 166 forks source link

The parameters 'exo_dim' and 'exo_shape' in the class 'NBeatsNet' #55

Closed helonin closed 2 years ago

helonin commented 3 years ago

Thanks for the great repository. I have a question: what is the parameters 'exo_dim' and 'exo_shape' in the class 'NBeatsNet' mean? How to use these extra variable? Thanks for your help.

philipperemy commented 2 years ago

First of all thank you :)

Exogenous variables are external variables, useful in the training and predictions. They are fed along with the inputs.

I added an example on how to use them:

https://github.com/philipperemy/n-beats/blob/master/examples/exo_example.py

It should be much clearer for you. Let me know if you need extra help!